no code implementations • NeurIPS 2015 • Kai Fan, Ziteng Wang, Jeff Beck, James Kwok, Katherine A. Heller
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well.
no code implementations • 9 Sep 2015 • Kai Fan, Ziteng Wang, Jeff Beck, James Kwok, Katherine Heller
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well.
no code implementations • NeurIPS 2013 • Agnieszka Grabska-Barwinska, Jeff Beck, Alexandre Pouget, Peter Latham
Thus, at the behavioral level, the two algorithms make very similar predictions.
no code implementations • NeurIPS 2012 • Charles Blundell, Jeff Beck, Katherine A. Heller
We present a Bayesian nonparametric model that discovers implicit social structure from interaction time-series data.
no code implementations • NeurIPS 2012 • Jeff Beck, Alexandre Pouget, Katherine A. Heller
This ability requires a neural code that represents probability distributions and neural circuits that are capable of implementing the operations of probabilistic inference.